Automotive / AI Voice SaaS
Otto Revenue Engine
A multi-tenant AI voice and CRM SaaS that automates inbound dealership calls, recovering revenue lost to missed calls and dropped follow-ups.
- Python
- FastAPI
- PostgreSQL
- Celery
- React 18
- TypeScript
- Auth0
- Twilio
- WebSockets
- Docker
The problem
Dealerships were losing revenue to missed inbound calls and dropped follow-ups.
What I built
An AI voice agent that answers inbound calls, books appointments through real-time tool calling and persists transcripts, on two voice providers behind one switchable abstraction.
My role
- Built the multi-tenant platform
- Voice pipeline and telephony webhooks
- Real-time tool calling for bookings
- Provider-agnostic voice abstraction
Technical highlights
- Signature-verified telephony webhooks
- Retell and x.AI Grok realtime over Twilio Media Streams, behind one switch
- Zero-downtime migration between voice providers
- Call transcripts persisted